[CI] Migrate CUDA Graph tests to test/registered/cuda_graph/ (#15436)

.github/workflows/pr-test.yml

@@ -448,12 +448,49 @@ jobs:
           cd test/
           python3 run_suite.py --hw cuda --suite stage-b-test-small-1-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 3
 
-  stage-b-test-2-gpu:
+  stage-b-test-large-1-gpu:
     needs: [check-changes, call-gate, stage-a-test-1, sgl-kernel-build-wheels]
     if: |
       always() &&
       (
-        (inputs.target_stage == 'stage-b-test-2-gpu') ||
+        (inputs.target_stage == 'stage-b-test-large-1-gpu') ||
+        (
+          !inputs.target_stage &&
+          (github.event_name == 'schedule' || (!failure() && !cancelled())) &&
+          ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
+        )
+      )
+    runs-on: 1-gpu-runner
+    env:
+      RUNNER_LABELS: 1-gpu-runner
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Download artifacts
+        if: needs.check-changes.outputs.sgl_kernel == 'true'
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 30
+        run: |
+          cd test/
+          python3 run_suite.py --hw cuda --suite stage-b-test-large-1-gpu
+
+  stage-b-test-large-2-gpu:
+    needs: [check-changes, call-gate, stage-a-test-1, sgl-kernel-build-wheels]
+    if: |
+      always() &&
+      (
+        (inputs.target_stage == 'stage-b-test-large-2-gpu') ||
         (
           !inputs.target_stage &&
           (github.event_name == 'schedule' || (!failure() && !cancelled())) &&
@@ -483,7 +520,7 @@ jobs:
         timeout-minutes: 30
         run: |
           cd test/
-          python3 run_suite.py --hw cuda --suite stage-b-test-small-2-gpu
+          python3 run_suite.py --hw cuda --suite stage-b-test-large-2-gpu
 
   multimodal-gen-test-1-gpu:
     needs: [check-changes, call-gate, sgl-kernel-build-wheels]
@@ -1363,7 +1400,8 @@ jobs:
 
         stage-a-test-1,
         stage-b-test-small-1-gpu,
-        stage-b-test-2-gpu,
+        stage-b-test-large-1-gpu,
+        stage-b-test-large-2-gpu,
         quantization-test,
         unit-test-backend-1-gpu,
         unit-test-backend-2-gpu,